Date:   Thu,  6 Jan 2022 12:20:39 -0500
In-Reply-To: <20220106172041.522167-1-brho@google.com>
Message-Id: <20220106172041.522167-2-brho@google.com>
Mime-Version: 1.0
References: <20220106172041.522167-1-brho@google.com>
Subject: [PATCH v3 1/3] setpriority: only grab the tasklist_lock for PRIO_PGRP
From:   Barret Rhoden <brho@google.com>
To:     ebiederm@xmission.com
Cc:     Christian Brauner <christian.brauner@ubuntu.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Alexey Gladkov <legion@kernel.org>,
        William Cohen <wcohen@redhat.com>,
        Viresh Kumar <viresh.kumar@linaro.org>,
        Alexey Dobriyan <adobriyan@gmail.com>,
        Chris Hyser <chris.hyser@oracle.com>,
        Peter Collingbourne <pcc@google.com>,
        Xiaofeng Cao <caoxiaofeng@yulong.com>,
        David Hildenbrand <david@redhat.com>,
        Cyrill Gorcunov <gorcunov@gmail.com>,
        linux-kernel@vger.kernel.org
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

The tasklist_lock is necessary only for PRIO_PGRP for both setpriority()
and getpriority().

Unnecessarily grabbing the tasklist_lock can be a scalability bottleneck
for workloads that also must grab the tasklist_lock for waiting,
killing, and cloning.

This change resulted in a 12% speedup on a microbenchmark where parents
kill and wait on their children, and children getpriority, setpriority,
and getrlimit.

Signed-off-by: Barret Rhoden <brho@google.com>
---
 kernel/sys.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/kernel/sys.c b/kernel/sys.c
index 8fdac0d90504..558e52fa5bbd 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -220,7 +220,6 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval)
 		niceval = MAX_NICE;
 
 	rcu_read_lock();
-	read_lock(&tasklist_lock);
 	switch (which) {
 	case PRIO_PROCESS:
 		if (who)
@@ -231,6 +230,7 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval)
 			error = set_one_prio(p, niceval, error);
 		break;
 	case PRIO_PGRP:
+		read_lock(&tasklist_lock);
 		if (who)
 			pgrp = find_vpid(who);
 		else
@@ -238,6 +238,7 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval)
 		do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
 			error = set_one_prio(p, niceval, error);
 		} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
+		read_unlock(&tasklist_lock);
 		break;
 	case PRIO_USER:
 		uid = make_kuid(cred->user_ns, who);
@@ -258,7 +259,6 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval)
 		break;
 	}
 out_unlock:
-	read_unlock(&tasklist_lock);
 	rcu_read_unlock();
 out:
 	return error;
@@ -283,7 +283,6 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who)
 		return -EINVAL;
 
 	rcu_read_lock();
-	read_lock(&tasklist_lock);
 	switch (which) {
 	case PRIO_PROCESS:
 		if (who)
@@ -297,6 +296,7 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who)
 		}
 		break;
 	case PRIO_PGRP:
+		read_lock(&tasklist_lock);
 		if (who)
 			pgrp = find_vpid(who);
 		else
@@ -306,6 +306,7 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who)
 			if (niceval > retval)
 				retval = niceval;
 		} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
+		read_unlock(&tasklist_lock);
 		break;
 	case PRIO_USER:
 		uid = make_kuid(cred->user_ns, who);
@@ -329,7 +330,6 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who)
 		break;
 	}
 out_unlock:
-	read_unlock(&tasklist_lock);
 	rcu_read_unlock();
 
 	return retval;
-- 
2.34.1.448.ga2b2bfdf31-goog